{"id":"https://openalex.org/W2166618252","doi":"https://doi.org/10.1109/icsmc.2009.5345891","title":"Learning to generalize and reuse skills using approximate partial policy homomorphisms","display_name":"Learning to generalize and reuse skills using approximate partial policy homomorphisms","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2166618252","doi":"https://doi.org/10.1109/icsmc.2009.5345891","mag":"2166618252"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2009.5345891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2009.5345891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086910136","display_name":"Srividhya Rajendran","orcid":null},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srividhya Rajendran","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047174917","display_name":"Manfred Huber","orcid":"https://orcid.org/0009-0007-0294-9147"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manfred Huber","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Texas, Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189196454"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"112","issue":null,"first_page":"2239","last_page":"2244"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9800999760627747,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9717000126838684,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/homomorphism","display_name":"Homomorphism","score":0.8150932788848877},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8106702566146851},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7335187792778015},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6589764356613159},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5801650881767273},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5772845149040222},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5460314154624939},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5426211357116699},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48513683676719666},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.48191025853157043},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.44870156049728394},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41729283332824707},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.4132523536682129},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.26236259937286377},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11474841833114624}],"concepts":[{"id":"https://openalex.org/C4042151","wikidata":"https://www.wikidata.org/wiki/Q215111","display_name":"Homomorphism","level":2,"score":0.8150932788848877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8106702566146851},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7335187792778015},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6589764356613159},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5801650881767273},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5772845149040222},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5460314154624939},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5426211357116699},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48513683676719666},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.48191025853157043},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.44870156049728394},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41729283332824707},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.4132523536682129},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26236259937286377},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11474841833114624},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2009.5345891","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2009.5345891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Systems, Man and Cybernetics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1666476","https://openalex.org/W79394677","https://openalex.org/W266716723","https://openalex.org/W336646847","https://openalex.org/W1492014007","https://openalex.org/W1534331386","https://openalex.org/W1578521162","https://openalex.org/W1592847719","https://openalex.org/W1822705290","https://openalex.org/W1992764401","https://openalex.org/W2109910161","https://openalex.org/W2118022839","https://openalex.org/W3011120880","https://openalex.org/W6600058601","https://openalex.org/W6603137543","https://openalex.org/W6629461247","https://openalex.org/W6632173739","https://openalex.org/W6634579893","https://openalex.org/W6638398152","https://openalex.org/W6677738694","https://openalex.org/W6775686901","https://openalex.org/W7075606714"],"related_works":["https://openalex.org/W4308159138","https://openalex.org/W4327811209","https://openalex.org/W1979798674","https://openalex.org/W3169947911","https://openalex.org/W3037616202","https://openalex.org/W2963079901","https://openalex.org/W390508480","https://openalex.org/W2294450783","https://openalex.org/W2375240985","https://openalex.org/W2087709123"],"abstract_inverted_index":{"A":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"agent":[4],"that":[5,71],"performs":[6],"successfully":[7],"in":[8,109,148,201,224],"a":[9,54,67,121,130,177,228],"complex":[10],"and":[11,18,33,61,107,175,197,216],"dynamic":[12],"environment":[13],"has":[14],"to":[15,20,28,42,47,57,79,91,101,151,162,184,220],"continuously":[16],"learn":[17,48,221],"adapt":[19],"perform":[21],"new":[22,49,55,149,153,185,203,222],"tasks.":[23,50,157],"This":[24,51],"necessitates":[25],"for":[26,120,136,190],"them":[27],"not":[29],"only":[30],"extract":[31,58],"control":[32,60],"representation":[34],"knowledge":[35,46,183,192],"from":[36,129],"the":[37,44,73,87,168,172,181,188,194,198,202,207],"tasks":[38,106,125,165,223],"learned,":[39],"but":[40],"also":[41,160],"reuse":[43,219],"extracted":[45],"paper":[52,84],"presents":[53],"method":[56],"this":[59],"representational":[62],"knowledge.":[63],"Here":[64],"we":[65],"present":[66],"policy":[68,77,88,98,114,119,144,210,214,218],"generalization":[69,99],"approach":[70,159],"uses":[72],"novel":[74,225],"concept":[75],"of":[76,123,132,155,171,179,193,209,230],"homomorphism":[78,89,115,215],"derive":[80],"these":[81],"abstractions.":[82],"The":[83,95,112,141,158],"further":[85],"extends":[86],"framework":[90,100],"an":[92,117],"approximate":[93,113,213],"policy.":[94],"extension":[96],"allows":[97,161],"efficiently":[102],"address":[103,152],"more":[104],"realistic":[105],"environments":[108],"non-deterministic":[110],"domains.":[111],"derives":[116],"abstract":[118],"set":[122,131,229],"similar":[124,164],"(a":[126],"task":[127,139],"type)":[128],"basic":[133],"policies":[134],"learned":[135,182],"previously":[137],"seen":[138],"instances.":[140],"resulting":[142],"generalized":[143],"is":[145],"then":[146],"applied":[147],"contexts":[150],"instances":[154],"related":[156],"identify":[163],"based":[166],"on":[167],"functional":[169],"characteristics":[170],"corresponding":[173],"skills":[174],"provides":[176],"means":[178],"transferring":[180],"situations":[186,226],"without":[187],"need":[189],"complete":[191],"state":[195],"space":[196],"system":[199],"dynamics":[200],"environment.":[204],"We":[205],"demonstrate":[206],"working":[208],"abstraction":[211],"using":[212,227],"illustrate":[217],"grid":[231],"world":[232],"examples.":[233]},"counts_by_year":[{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}